Generative AI-based sand storm weather prediction method, system and device, and medium

Abstract

The invention discloses a sand storm weather prediction method, system and device based on generative AI and a medium, and relates to the technical field of sand storm prediction. The method comprises the steps that an MM-DDPM model is constructed, the MM-DDPM model is utilized to jointly encode the relevance between meteorological elements and sand storm labels in a sand storm data set, and a sand storm enhanced sample is generated; performing parameter adjustment and optimization on the pre-trained meteorological large model by using the sand storm enhanced sample to obtain a trained sand storm prediction model, and performing weather prediction by using the sand storm prediction model to obtain a sand storm prediction result; the sand storm prediction result comprises occurrence time, duration time and spatial distribution of a sand storm event; the pre-trained meteorological large model is constructed based on a Fengwu model and a sand storm fitting layer. According to the method, the limitation of the prior art on data scarcity and imbalance can be broken through by generating the reliable sand storm data sample, and the precision and stability of sand storm prediction are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of sandstorm prediction, and in particular to a sandstorm weather prediction method, system, device and medium based on generative AI. Background Art

[0002] In the field of sandstorm weather prediction, existing methods are mainly divided into numerical prediction methods based on physical models and statistical prediction methods based on machine learning. However, these methods have significant limitations in dealing with sparse and unbalanced data samples.

[0003] Numerical prediction methods based on physical models are currently a commonly used technology in meteorological forecasting, which mainly relies on the simulation of atmospheric physical processes. Common physical models such as the WRF (Weather Research and Forecasting) model simulate the movement and evolution of the atmosphere by solving a series of complex atmospheric dynamics and thermodynamic equations. Although this type of method can theoretically capture the physical essence of weather processes, it has the following shortcomings: (1) High computational cost: Numerical prediction models are complex and require a large amount of computing resources, especially in extreme weather events such as sandstorms that involve multiple atmospheric processes. The computational cost is high and the time requirements are strict; (2) Accuracy depends on model parameters: The accuracy of numerical models depends on the initial conditions and the setting of model parameters. These parameters are often difficult to accurately obtain or adjust, resulting in insufficient accuracy in the prediction of local extreme weather events (such as sandstorms).

[0004] In recent years, with the rise of data-driven technology, artificial intelligence (AI) methods represented by machine learning have been widely used in weather forecasting, such as PanguWeather, Fengwu, Fuxi, Graphcast and other large weather models. By using historical meteorological data to train models, machine learning methods can identify patterns in data and predict future weather. However, existing machine learning methods still face many challenges in sandstorm prediction: (1) Strong data dependence: Machine learning models are highly dependent on a large amount of training data, but the occurrence of sandstorm events is scarce, and data samples are usually small and unbalanced, which makes it difficult for the model to fully learn the laws of sandstorm occurrence, resulting in overfitting or unstable prediction problems; (2) Lack of physical information fusion: Most machine learning models only focus on the statistical patterns of the data itself, fail to effectively combine atmospheric physical processes, and find it difficult to capture the complex meteorological background when sandstorms occur, limiting their prediction accuracy.

[0005] In recent years, generative AI technologies such as Generative Adversarial Network (GAN) and Variational Autoencoder (VAE) have performed well in solving the problem of data imbalance and can enhance the diversity of data sets by generating virtual samples. These technologies have achieved good results in some fields, but they still have the following shortcomings in sandstorm weather forecasting: (1) Single-modal generation: Existing generative AI methods usually only generate a single type of data and fail to consider the joint generation of multiple meteorological elements at the same time, which makes the match between the generated virtual data and the actual meteorological conditions not high, affecting the reliability of the generated data; (2) Insufficient physical consistency: Traditional generative models mostly ignore the physical constraints in meteorological data, and the generated virtual data may not conform to the actual physical laws, which limits their application in meteorological forecasting.

[0006] In view of the limitations of these existing technologies, how to generate sandstorm data samples that can match the meteorological conditions has become a major challenge in existing technologies. Summary of the invention

[0007] The purpose of the present invention is to provide a sandstorm weather prediction method, system, device and medium based on generative AI, which can break through the limitations of existing technologies in data scarcity and imbalance by generating reliable sandstorm data samples, and improve the accuracy and stability of sandstorm prediction.

[0008] To achieve the above object, the present invention provides the following solutions:

[0009] A sandstorm weather prediction method based on generative AI, comprising:

[0010] Obtain dust storm datasets from historical data;

[0011] A MM-DDPM model is constructed, and the MM-DDPM model is used to jointly encode the correlation between the meteorological elements and the sandstorm labels in the sandstorm dataset to generate sandstorm enhanced samples; the sandstorm enhanced samples include meteorological element data and sandstorm data with physical correlation; the MM-DDPM model is constructed based on a joint encoder and a joint loss;

[0012] The sandstorm enhancement samples are used to tune the parameters of the pre-trained meteorological model to obtain a trained sandstorm prediction model, and the sandstorm prediction model is used to perform weather forecasting to obtain sandstorm prediction results; the sandstorm prediction results include the occurrence time, duration and spatial distribution of sandstorm events; the pre-trained meteorological model is constructed based on the Fengwu model and the sandstorm fitting layer.

[0013] Optionally, the historical data adopts the sandstorm data set LSDSSIMR data constructed by FY-4A satellite impact and meteorological reanalysis data, and ERA5 meteorological data.

[0014] Optionally, the specific generation process of the sandstorm enhanced sample is:

[0015] The meteorological element data X w and sandstorm data X d By combining the encoder E(X d , X w ) is converted into a shared latent variable space representation Z, and the data of the two modes are mapped to the same latent variable space through the joint encoder, so as to achieve modeling and preserve the relationship between the two modes in the diffusion process; in the forward diffusion process, noise is gradually added to the latent variable Z to make its distribution close to the standard Gaussian distribution Specifically expressed as:

[0016]

[0017] In the formula, Z t is the latent variable representation of the diffusion process at time t, where t belongs to the integer range [0, T]; the reverse generation process starts from the latent variable Z after adding the maximum Gaussian noise T At the beginning, the initial joint latent variable representation Z0 is gradually denoised and restored to generate sandstorm data related to meteorological conditions. The conditional probability distribution generated in reverse is:

[0018]

[0019] In the formula, μ θ and Σ θ are the mean and covariance matrices respectively, depending on the current latent variable representation Z t And weather data X w The generated final latent variable representation Z0 is used to restore the meteorological elements through the decoder D and sandstorm data

[0020] Optionally, the joint loss is expressed as:

[0021]

[0022] Among them, the first term represents the reconstruction loss in the latent variable space, the second and third terms represent the reconstruction losses of meteorological data and sandstorm data respectively, and λ1 and λ2 are both loss balance coefficients. represents the expected value of the latent variable reconstruction loss under the conditions of joint time t, latent variable space Z0, and noise ∈, and Respectively represent the meteorological data Xw and sandstorm data X d The expectation of the reconstruction error.

[0023] Optionally, the specific process of weather forecasting by the sandstorm prediction model is as follows:

[0024] In the sandstorm prediction model, the input data is mapped to the joint latent variable space H through a layer of Transformer shared encoder, which is expressed as:

[0025]

[0026] in, Indicates that the Fengwu model is The output result is the input. Subsequently, the fully connected fitting layer is used to map the future meteorological elements to the probability of sandstorm occurrence, and the probability of sandstorm occurrence is output through the Sigmoid activation function:

[0027] Output=σ(W2·ReLU(W1·H+b1)+b2)

[0028] Among them, W1, W2 and b1, b2 are the weights and biases of the network, σ is the Sigmoid activation function, and the output Output represents the probability of sandstorm occurrence; since the sandstorm data is binary data, the binary cross entropy loss function is used to optimize the model, and the expression of the loss function is:

[0029]

[0030] Among them, y i For real sandstorm labels, The probability of sandstorm occurrence predicted by the model. In the sandstorm prediction model, the main part of the meteorological model is frozen and no longer participates in the training. Only the parameters are tuned on the sandstorm fitting layer to approximate the sandstorm data. The enhanced samples generated by the MM-DDPM model are used to solve the data imbalance problem. During the parameter tuning process, the enhanced samples and the real sandstorm data are input into the model together, so that the fitting layer can more accurately capture the sandstorm occurrence pattern. After the parameter tuning is completed, the sandstorm prediction model is used to predict the occurrence of sandstorms in the future time step. Among them, the input meteorological element X T+1:T+K , the model outputs the probability of sandstorms occurring in the future as:

[0031]

[0032] in, is the probability of sandstorm occurrence in the next K time steps, M DustNet The final sandstorm prediction model.

[0033] The present invention also provides a sandstorm weather prediction system based on generative AI, comprising:

[0034] Data collection module, used to obtain sandstorm data sets from historical data;

[0035] A sample enhancement module, used for constructing an MM-DDPM model, and using the MM-DDPM model to jointly encode the correlation between the meteorological elements and the sandstorm labels in the sandstorm dataset to generate sandstorm enhanced samples; the sandstorm enhanced samples include meteorological element data and sandstorm data with physical correlation; the MM-DDPM model is constructed based on a joint encoder and a joint loss;

[0036] The weather forecast module is used to use the sandstorm enhancement sample to tune the parameters of the pre-trained meteorological model to obtain a trained sandstorm prediction model, and use the sandstorm prediction model to perform weather forecasting to obtain sandstorm prediction results; the sandstorm prediction results include the occurrence time, duration and spatial distribution of the sandstorm event; the pre-trained meteorological model is constructed based on the Fengwu model and the sandstorm fitting layer.

[0037] The present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the above-mentioned sandstorm weather prediction method based on generative AI.

[0038] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the sandstorm weather prediction method based on generative AI as described above.

[0039] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0040] The present invention discloses a sandstorm weather prediction method, system, device and medium based on generative AI, the method comprising constructing an MM-DDPM model, and using the MM-DDPM model to jointly encode the correlation between meteorological elements and sandstorm labels in a sandstorm data set to generate sandstorm enhancement samples; using the sandstorm enhancement samples to perform parameter tuning on a pre-trained meteorological large model to obtain a trained sandstorm prediction model, and using the sandstorm prediction model to perform weather prediction to obtain a sandstorm prediction result; the sandstorm prediction result includes the occurrence time, duration and spatial distribution of the sandstorm event; the pre-trained meteorological large model is constructed based on the Fengwu model and the sandstorm fitting layer. The present invention can break through the limitations of the existing technology in data scarcity and imbalance by generating reliable sandstorm data samples, and improve the accuracy and stability of sandstorm prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0042] Figure 1 It is a flow chart of the sandstorm weather prediction method based on generative AI of the present invention;

[0043] Figure 2 This is a schematic diagram of sample balancing based on the DDPM model in this embodiment;

[0044] Figure 3 Schematic diagram of the multimodal denoising diffusion probability model MM-DDPM model in this embodiment;

[0045] Figure 4 This is a schematic diagram of data flow during DustNet model training in this embodiment;

[0046] Figure 5 This is a comparison chart of the sandstorm prediction effect and the actual observation result on May 31, 2022 in this embodiment; among them, part (a) is the actual observation picture; part (b) is the prediction result picture. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] The purpose of the present invention is to provide a sandstorm weather prediction method, system, device and medium based on generative AI, which can break through the limitations of existing technologies in data scarcity and imbalance by generating reliable sandstorm data samples, and improve the accuracy and stability of sandstorm prediction.

[0049] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0050] The present invention provides a sandstorm weather prediction method based on generative AI, comprising:

[0051] Step 100: Obtain a sandstorm dataset from historical data.

[0052] Step 200: construct an MM-DDPM model, and use the MM-DDPM model to jointly encode the correlation between the meteorological elements and the sandstorm labels in the sandstorm dataset to generate sandstorm enhanced samples; the sandstorm enhanced samples include meteorological element data and sandstorm data with physical correlation; the MM-DDPM model is constructed based on a joint encoder and a joint loss.

[0053] Step 300: Use the sandstorm enhancement sample to tune the parameters of the pre-trained meteorological model to obtain a trained sandstorm prediction model, and use the sandstorm prediction model to perform weather forecasting to obtain sandstorm prediction results; the sandstorm prediction results include the occurrence time, duration and spatial distribution of the sandstorm event; the pre-trained meteorological model is constructed based on the Fengwu model and the sandstorm fitting layer.

[0054] It can be seen that in this embodiment, firstly, in view of the current situation that the sandstorm weather data set samples are scarce and unevenly distributed, a multimodal diffusion model is proposed to generate virtual sandstorm data samples, solve the problem of sample imbalance, and provide more diverse training data for the model; secondly, by introducing the existing high-precision pre-trained meteorological large model, using transfer learning technology, adding a sandstorm fitting layer on the basis of the pre-trained model, and constructing a DustNet model that deeply associates meteorological data with sandstorm events, the meteorological conditions are fully utilized to gain insight into the occurrence of future sandstorms, and the model's prediction accuracy and robustness for sandstorm weather are improved. Extreme weather events such as sandstorms have a serious impact on human production and life. Through the implementation of the present invention, it will make important contributions to reducing disaster losses and protecting people's lives and property.

[0055] Based on the above scheme, the following embodiments are provided.

[0056] like Figure 1 As shown, this embodiment combines a multimodal diffusion model with a large meteorological model to generate sandstorm samples that match real meteorological conditions, thereby improving the model's ability to predict sandstorm weather.

[0057] First, the study was conducted using the LSDSSIMR data, a sandstorm dataset constructed based on the FY-4A satellite impact and meteorological reanalysis data, and ERA5 meteorological data. The LSDSSIMR dataset covers most of the areas where sandstorms occur most frequently, with a spatial resolution of 4km and an image size of 640×1280. The data was collected at intervals of 15 minutes from March to May every year from 2020 to 2022, providing a large amount of research data for sandstorm research. Although LSDSSIMR provides rich research data, sandstorms are still extremely rare events. Therefore, in this embodiment, the sample balancing method is first explored to expand the meteorological elements and the number of sandstorm labels for sandstorms based on the generative AI-diffusion model, such as Figure 2 As shown in the figure. The DDPM model is a type of diffusion model. Through the process of forward diffusion and reverse denoising, the model fully learns the distribution of samples, and then generates new samples with the same distribution as the samples from the noise, achieving sample balance from the perspective of data enhancement. However, in the research task of inputting meteorological elements for sandstorm prediction, simply generating sandstorm label samples still cannot achieve an effective sample process. Therefore, it is necessary to develop a generation method that simultaneously generates meteorological elements and sandstorm label data and ensures that there is a realistic correlation between them.

[0058] Accordingly, the present invention first constructs a Multi-Model Denoising Diffusion Probabilistic Model (MM-DDPM model), which jointly encodes the correlation between meteorological elements and sandstorm labels, and simultaneously generates meteorological element data and sandstorm data with physical correlation, thereby achieving sample balance of the sandstorm data set. The MM-DDPM model not only retains the ability of the DDPM model to gradually denoise and generate data, but also introduces a multimodal information processing module into the model structure, so that the generated sandstorm data samples are consistent with the meteorological data. Compared with the conventional DDPM model, the MM-DDPM model takes into account more interdependencies between modes during the generation process. For example, the specific structure comparison Figure 3 The core idea of ​​the MM-DDPM model is to represent the joint distribution of meteorological elements and sandstorm data as part of the diffusion process based on conditional generation, and to generate sandstorm data that matches the meteorological conditions through reverse denoising. The implementation process is as follows:

[0059] First, the meteorological element data X w and sandstorm data X d By combining the encoder E(X d , X w) is converted into a shared latent variable space representation Z. This joint encoder ensures that the data of the two modalities are mapped to the same latent variable space, so that their mutual relationship during the diffusion process can be modeled and preserved. During the forward diffusion process, the latent variable Z is gradually added with noise to make its distribution close to the standard Gaussian distribution.

[0060]

[0061] In the formula, Z t is the latent variable representation of the diffusion process at time t, where t belongs to the integer range [0, T]; the reverse generation process starts from the latent variable Z after adding the maximum Gaussian noise T At the beginning, the initial joint latent variable representation Z0 is gradually denoised and restored to generate sandstorm data related to meteorological conditions. The conditional probability distribution generated in reverse is:

[0062]

[0063] In the formula, μ θ and Σ θ are the mean and covariance matrices respectively, depending on the current latent variable representation Z t And weather data X w The generated final latent variable representation Z0 can be restored to the meteorological elements through the decoder D and sandstorm data

[0064]

[0065] During the training process, the loss function of the MM-DDPM model is designed to reconstruct both meteorological data and sandstorm data simultaneously to ensure that the generated results are physically consistent:

[0066]

[0067] Among them, the first term represents the reconstruction loss in the latent variable space, the second and third terms represent the reconstruction losses of meteorological data and sandstorm data respectively, and λ1 and λ2 are the balance coefficients of the loss. represents the expected value of the latent variable reconstruction loss under the conditions of joint time t, latent variable space Z0, and noise ∈, and Respectively represent the meteorological data X w and sandstorm data X d By minimizing the loss function L and optimizing the model parameters θ, we can ensure that the generated meteorological and sandstorm data are physically consistent, and finally obtain the generated meteorological elements. and sandstorm data Through this joint encoding and diffusion mechanism, the MM-DDPM model can learn the complex correlation between meteorological elements and sandstorm data in the latent variable space, and simultaneously generate physically related data samples, thereby balancing the sandstorm data set and improving the generalization ability and prediction accuracy of the model.

[0068] After generating a virtual sandstorm dataset, meteorological elements are used to approximate the sandstorm label value based on the pre-trained meteorological model (taking Fengwu as an example). Since generating sandstorm data directly from future meteorological data obtained from the Fengwu model will lead to error accumulation, a combination of transfer learning and fine-tuning is adopted to adjust the model output by introducing a sandstorm fitting module to model the relationship between meteorological data and sandstorm events. Finally, the sandstorm weather prediction model DustNet is obtained through transfer learning and fine-tuning based on the meteorological model and sample balanced sandstorm data, as shown in the figure. Figure 4 shown.

[0069] First, in DustNet, the future meteorological elements predicted by the large meteorological model cannot be directly used for sandstorm prediction. Therefore, a sandstorm fitting layer is introduced to approximate the probability of sandstorm occurrence. In order to better map meteorological elements to sandstorm data, the model maps the input data to the joint latent variable space H through a layer of Transformer shared encoder, which is expressed as:

[0070]

[0071] in Fengwu is the output result of the input. Subsequently, a fully connected fitting layer is used to map future meteorological factors to the probability of sandstorms, and the probability of sandstorms is output through the Sigmoid activation function:

[0072] Output=σ(W2·ReLU(W1·H+b1)+b2)

[0073] Among them, W1, W2 and b1, b2 are the weights and biases of the network, σ is the Sigmoid activation function, and the output Output represents the probability of sandstorm occurrence. Since the sandstorm data is binary data, the binary cross entropy loss function is used to optimize the model. The expression of the loss function is:

[0074]

[0075] Among them, y i For real sandstorm labels, is the probability of occurrence of sandstorms predicted by the model. In DustNet, the main part of the meteorological model is frozen, that is, it is no longer involved in training. Only fine-tuning is performed on the sandstorm fitting layer to approximate the sandstorm data. The enhanced samples generated by the multimodal diffusion model can alleviate the data imbalance problem. During the fine-tuning process, the enhanced samples and the real sandstorm data are input into the model together, so that the fitting layer can more accurately capture the pattern of sandstorm occurrence. After fine-tuning, the DustNet model can predict the occurrence of sandstorms in future time steps. Specifically, the meteorological element X is input. T+1 :T+K, the model outputs the probability of future sandstorms:

[0076]

[0077] in, is the probability of sandstorm occurrence in the next K time steps, M DustNet The final DustNet model.

[0078] The technical solution in this embodiment generates virtual sandstorm data samples through the MM-DDPM model, solves the data imbalance problem, and builds the DustNet sandstorm prediction model to accurately predict the occurrence of future sandstorms. This method not only improves the prediction ability of the model, but also expands the application scope of existing large meteorological models. It has broad application prospects in extreme weather forecasting and is expected to provide scientific basis and technical support for scientific research and practical applications in the fields of meteorological forecasting and disaster prevention.

[0079] Therefore, the present invention innovatively solves the problem of scarce and unevenly distributed sandstorm data samples. By introducing a multimodal diffusion model (MM-DDPM model), the present invention can generate virtual sandstorm data samples that are consistent with actual physical conditions, significantly improve the diversity of the data set, and enhance the training effect of the model, thereby effectively improving the accuracy and generalization ability of sandstorm predictions. In addition, the present invention also freezes the backbone of the pre-trained meteorological model, adds a fitting layer specifically for fitting sandstorm data, and combines transfer learning technology to accurately approximate future meteorological elements to the occurrence of sandstorms. This process effectively avoids the phenomenon of gradual accumulation of errors, while greatly improving the accuracy of predictions and the robustness of the model.

[0080] Specifically, the MM-DDPM model generates virtual dust storm data to make up for the problem of scarce samples in the original dataset. Figure 5The sandstorm prediction results shown intuitively demonstrate the effectiveness and accuracy of the present invention. After the generated enhanced samples were used for model training, the prediction results of the model were highly consistent with the actual occurrence of sandstorms. The model not only successfully captured the occurrence time of sandstorm events, but also accurately predicted its duration and spatial distribution, demonstrating extremely high practical value. Compared with traditional methods, the present invention avoids the problem of gradual accumulation of errors during the prediction process by adding a fitting layer based on the pre-trained atmospheric model and combining it with fine-tuning technology, thereby ensuring the stability and reliability of sandstorm predictions. While improving the prediction accuracy, the present invention also greatly enhances the model's ability to cope with complex meteorological conditions.

[0081] Furthermore, the present invention innovatively proposes a sandstorm sample generation method based on a multimodal denoising probability diffusion model (MM-DDPM model), which can effectively generate virtual sandstorm data with physical consistency. The model jointly encodes meteorological elements and sandstorm label data to generate virtual samples that match actual meteorological conditions, thereby compensating for the problem of sparse samples and uneven distribution of sandstorm datasets. This innovation is that the diversity of the dataset is improved through the generated virtual data, providing more sample support for the training of the sandstorm prediction model.

[0082] In addition, the present invention proposes a method based on transfer learning, introduces a pre-trained meteorological large model (taking FengWu as an example) to construct a sandstorm meteorological large model DustNet. By freezing the main part of the meteorological large model and adding a fitting layer that specifically fits sandstorm events, future meteorological elements are deeply associated with the occurrence of sandstorms. The fitting layer approaches future meteorological forecast data to sandstorm data through nonlinear mapping of meteorological elements, effectively avoiding the problem of error accumulation and enhancing the prediction accuracy of the model. This design effectively shortens the model training time and improves the specificity of sandstorm prediction through transfer learning technology. By using the enhanced samples generated by the MM-DDPM model, the model can achieve sample balance during the training process, further improving the generalization ability of the prediction model. The fine-tuning process targets the binarization characteristics of sandstorm data and combines the generated data for label fitting, thereby ensuring the accuracy and reliability of the prediction results.

[0083] The sandstorm prediction model DustNet structure proposed in the present invention is based on a pre-trained meteorological model and combined with a fitting layer. It establishes a complex relationship between meteorological elements and sandstorm events through a multi-layer network structure, and has high prediction accuracy and robustness. The DustNet model can predict the time and location of future sandstorm events by inputting meteorological element data within a certain time span, significantly improving the ability to predict extreme weather events.

[0084] The present invention effectively solves the problems of unbalanced sandstorm data and low prediction accuracy by combining technical key points and innovative points, and has broad application prospects in the fields of meteorological forecasting and disaster prevention.

[0085] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0086] This article uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A sandstorm weather prediction method based on generative AI, characterized in that: include: Obtain dust storm datasets from historical data; A MM-DDPM model is constructed, and the MM-DDPM model is used to jointly encode the correlation between the meteorological elements and the sandstorm labels in the sandstorm dataset to generate sandstorm enhanced samples; the sandstorm enhanced samples include meteorological element data and sandstorm data with physical correlation; the MM-DDPM model is constructed based on a joint encoder and a joint loss; The sandstorm enhancement samples are used to tune the parameters of the pre-trained meteorological model to obtain a trained sandstorm prediction model, and the sandstorm prediction model is used to perform weather forecasting to obtain sandstorm prediction results; the sandstorm prediction results include the occurrence time, duration and spatial distribution of sandstorm events; the pre-trained meteorological model is constructed based on the Fengwu model and the sandstorm fitting layer.

2. The sandstorm weather prediction method based on generative AI according to claim 1 is characterized in that: The historical data adopts the sandstorm data set LSDSSIMR data constructed by FY-4A satellite impact and meteorological reanalysis data, and ERA5 meteorological data.

3. The sandstorm weather prediction method based on generative AI according to claim 1 is characterized in that: The specific generation process of the sandstorm enhanced sample is as follows: The meteorological element data X w and sandstorm data X d By combining the encoder E(X d , X w ) is converted into a shared latent variable space representation Z, and the data of the two modes are mapped to the same latent variable space through the joint encoder, so as to achieve modeling and preserve the relationship between the two modes in the diffusion process; in the forward diffusion process, noise is gradually added to the latent variable Z to make its distribution close to the standard Gaussian distribution Specifically expressed as: In the formula, Z t is the latent variable representation of the diffusion process at time t, where t belongs to the integer range [0, T]; the reverse generation process starts from the latent variable Z after adding the maximum Gaussian noise T At the beginning, the initial joint latent variable representation Z0 is gradually denoised and restored to generate sandstorm data related to meteorological conditions. The conditional probability distribution generated in reverse is: In the formula, μ θ and Σ θ are the mean and covariance matrices respectively, depending on the current latent variable representation Z t And weather data X w The generated final latent variable representation Z0 is used to restore the meteorological elements through the decoder D and sandstorm data 4. The sandstorm weather prediction method based on generative AI according to claim 1 is characterized in that: The combined loss is expressed as: Among them, the first term represents the reconstruction loss in the latent variable space, the second and third terms represent the reconstruction losses of meteorological data and sandstorm data respectively, and λ1 and λ2 are both loss balance coefficients. represents the expected value of the latent variable reconstruction loss under the conditions of joint time t, latent variable space Z0, and noise ∈, and Respectively represent the meteorological data X w and sandstorm data X d The expectation of the reconstruction error.

5. The sandstorm weather prediction method based on generative AI according to claim 1 is characterized in that: The specific process of weather forecasting by the sandstorm prediction model is as follows: In the sandstorm prediction model, the input data is mapped to the joint latent variable space H through a layer of Transformer shared encoder, which is expressed as: in, Indicates that the Fengwu model is The output result is the input. Subsequently, the fully connected fitting layer is used to map the future meteorological elements to the probability of sandstorms, and the probability of sandstorms is output through the Sigmoid activation function: Output=σ(W2·ReLU(W1·H+b1)+b2) Among them, W1, W2 and b1, b2 are the weights and biases of the network, σ is the Sigmoid activation function, and the output Output represents the probability of sandstorm occurrence; since the sandstorm data is binary data, the binary cross entropy loss function is used to optimize the model, and the expression of the loss function is: Among them, y i For real sandstorm labels, The probability of sandstorm occurrence predicted by the model. In the sandstorm prediction model, the main part of the meteorological model is frozen and no longer participates in the training. Only the parameters are tuned on the sandstorm fitting layer to approximate the sandstorm data. The enhanced samples generated by the MM-DDPM model are used to solve the data imbalance problem. During the parameter tuning process, the enhanced samples and the real sandstorm data are input into the model together, so that the fitting layer can more accurately capture the sandstorm occurrence pattern. After the parameter tuning is completed, the sandstorm prediction model is used to predict the occurrence of sandstorms in the future time step. Among them, the input meteorological element X T+1:T+K , the model outputs the probability of sandstorms occurring in the future as: in, is the probability of sandstorm occurrence in the next K time steps, M DustNet The final sandstorm prediction model.

6. A sandstorm weather prediction system based on generative AI, characterized in that: include: Data collection module, used to obtain sandstorm data sets from historical data; A sample enhancement module, used for constructing an MM-DDPM model, and using the MM-DDPM model to jointly encode the correlation between the meteorological elements and the sandstorm labels in the sandstorm dataset to generate sandstorm enhanced samples; the sandstorm enhanced samples include meteorological element data and sandstorm data with physical correlation; the MM-DDPM model is constructed based on a joint encoder and a joint loss; The weather forecast module is used to use the sandstorm enhancement sample to tune the parameters of the pre-trained meteorological model to obtain a trained sandstorm prediction model, and use the sandstorm prediction model to perform weather forecasting to obtain sandstorm prediction results; the sandstorm prediction results include the occurrence time, duration and spatial distribution of the sandstorm event; the pre-trained meteorological model is constructed based on the Fengwu model and the sandstorm fitting layer.

7. An electronic device, characterized in that: It includes a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the sandstorm weather prediction method based on generative AI according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the sandstorm weather prediction method based on generative AI as described in any one of claims 1 to 5.

Images